Handwritten Digit Recognition
Journal: International Journal of Trend in Scientific Research and Development (Vol.2, No. 2)Publication Date: 2018-08-01
Authors : Jyoti Shinde Chaitali Rajput Mrunal Shidore Milind Rane;
Page : 608-611
Keywords : Electronics & Communication Engineering;
Abstract
The main objective of this paper is to recognize and predict handwritten digits from 0 to 9 where data set of 5000 examples of MNIST was given as input. As we know as every person has different style of writing digits humans can recognize easily but for computers it is comparatively a difficult task so here we have used neural network approach where in the machine will learn on itself by gaining experiences and the accuracy will increase based upon the experience it gains. The dataset was trained using feed forward neural network algorithm. The overall system accuracy obtained was 95.7% Jyoti Shinde | Chaitali Rajput | Prof. Mrunal Shidore | Prof. Milind Rane"Handwritten Digit Recognition" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-2 , February 2018, URL: http://www.ijtsrd.com/papers/ijtsrd8384.pdf http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/8384/handwritten-digit-recognition/jyoti-shinde
Other Latest Articles
- Impact of Exchange Rate on the Performance of Small and Medium Enterprises in Nigeria
- Effect of Small and Medium Enterprises on Employment Generation in Nigeria
- Holistic Security for Internet-of-Things (IoTs) Implementation in Nigeria
- A Review on Aspects of Dental Drug Delivery
- Direct Cash Transfer to Resolve the Crisis of Income Inequality
Last modified: 2018-08-02 14:32:39